Havuz

A modern, local-first AI roleplay platform

Zero Code Studio 是一个工程化 AI 代码生成平台，基于 Spring Boot、LangChain4j、LangGraph4j，支持工具调用、Workflow 编排、任务计划规划、三层上下文压缩、SSE 过程可视化、定点修改与一键本地部署。

Open benchmark on observability tasks built on Harbor

Embodied AI companion for Minecraft — persistent memory, vision, learning, multi-agent. Built on Hermes Agent.

赛博人物库 · 把中国互联网最有辨识度的人物蒸馏成 AI Skill / Claude Code Skill / LLM character distillation

Local proxy that learns your app's typed LLM decisions and answers them with a Laya head. Jev and OpenAI compatible.

A wiki designed for both humans and agents to read and write.

PortableLM — Zero-dependency, air-gapped local AI that runs entirely from a USB drive. Chat, generate images, and synthesize speech offline

Craft is a Claude Code plugin that asks you the product questions and works out the technical ones. Features get planned, built, and tested,

Turn documents into structured JSON with local-first document AI. Run 100% locally by default, with API, CLI, and Web UI.

An Elixir/OTP AI agent runtime: define agents, connect any OpenAI-compatible model, and run a tool-calling loop. CLI, HTTP API, web dashboar

LLM benchmark and leaderboard for narrator-bias sycophancy, opposite-narrator contradictions, and judgment consistency.

Talk to anyone: /coach persona plugin for Claude Code — research any public figure from their YouTube + web, then talk to them

OpenAI-compatible gateway aggregating 8 free LLM providers with automatic failover, circuit breakers, and smart routing. 32+ models, zero c

Add a talking 3D AI avatar to any web app. Samples and tools for the Perxona Connect SDK: <sv-presenter> web component, lip-sync, text-to-sp

CodeMonk 🥋 —>An open-source AI powered code intelligence platform that helps developers understand, explore, and navigate complex codebases

Generative UI SDK for Swift (genui)

Knowledge-graph RAG built from structured metadata instead of LLM extraction. 929M edges, zero LLM calls, 83.2% on held-out PubMedQA. Case s

Agent Harness for long-running agents that remember, continue, and learn from real work.

Tricorder provides simple, fast, focused feedback when hacking on Haskell (with or without LLM agents).

Find and repair substance defects in AI-assisted prose, code, docs, and agent output. Reports defects, never authorship. Structural tests ov

Run Kimi K3 (2.8 T parameters,1.56 TB) on iPhone 16 Pro? Weights stream from your SSD through a memory budget you set. Free, local, on Mac a

Open-source Legal AI workspace for evidence-grounded legal drafting, matter analysis and verifiable answers.

Local-first AI teaching assistant for editable lesson drafts, student materials, and slides. Uses your curriculum and chosen model. Teacher-

Cut context bloat in your AI-agent stack: find and safely prune unused skills, MCP servers and subagents from real transcript evidence

The coding agent you don’t have to watch. Start a task and walk away. AFK builds the feature, verifies its own work, and texts you when it’s

Grabs all your Perplexity conversations data, spits it out into a nice file folder structure and allows you to find your old conversations a

Code for DrivingBench: AI models drive real cars (comma/openpilot, Toyota and Tesla) through MCP tools, a runner loop for API models and tra

Keep private data, internal infrastructure and secrets out of cloud coding agents without breaking your workflow.

Turn any document into clean, AI-ready Markdown — locally on your machine. Desktop app for Windows, macOS & Linux powered by MarkItDown, Doc

Production-ready, bleeding-edge, upstream-first vLLM Docker image for the NVIDIA DGX Spark (GB10 / sm_121a), verified against real models on

A terminal AI agent you can fully undo - every file and shell action is snapshotted and reversible. Model-agnostic (any LLM), and connects t

MIT-licensed TypeScript runtime for AI-native game characters and worlds, with durable state, reliable actions, memory, tools, and Unity, Go

The self-hosted, multi-tenant AI app builder for teams. Sandboxed, audit-logged, MIT-licensed. The open-source alternative to Multi-Tenant S

Build LLM systems you actually control. A free, open engineering book + course — from tokenization to serving your own models. Mechanisms, t

📊 Automated hourly benchmarks for 20+ NVIDIA NIM models — interactive dashboard, zero infra, self-hostable. Open-source & community-driven.

Karpathy-inspired coding-agent guidelines packaged for Claude Code, Codex, Cursor, Gemini, OpenCode, Aider, Copilot, OpenClaw, and any AGENT

Neuroscience-inspired memory framework for AI agents

Open-source SEO audit agent — real-browser checks, backlink scoring, and multi-engine AI citation tracking (Claude, ChatGPT, Gemini, Perplex

The models on your disk, put to work. A private desktop app for open models — chat, a coding agent built for small models, text-to-image, te

Открытый бенчмарк LLM: какая нейросеть лучше пишет код 1С:Предприятие (BSL). Объективная оценка LLM по методике SMOP с реальным исполнением

[ACL 2026] PIArena: A Platform for Prompt Injection Evaluation

🤖 LLM Engineering Roadmap — Complete Developer Guide

Stockfish + LLM chess coach: an MCP server and web board that explain your mistakes in plain English

One command to turn any codebase into an MCP server

Agent-native Stata bridge for empirical research — run DiD/IV/RDD and publication-ready tables from Claude Code, Jupyter, or VS Code on one

A lightweight, system-wide AI text-selection assistant that supports custom LLM APIs and screenshot-based AI image recognition.轻量级系统全局ai划词助手

TerminalWorld: Benchmarking Agents on Real-World Terminal Tasks (NeurIPS 2026 Evaluations and Datasets Track)

ONE API，LLM_Proxy，统一代理，支持请求响应自定义转换。

OpenCode plugin for automatic API-key failover and rotation across multiple provider keys